© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37729
    Prev
    Next
    INDEX
    Explanations

    undervalued buying opportunities

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags words and phrases typical of value-investing or buying-opportunity talk—comparatives and quantifiers around “cheaper,” “better,” “decent dip,” “value investors,” “buying opportunity,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imagenes
    -0.90
     évidemment
    -0.86
    splan
    -0.81
     ados
    -0.80
    ggel
    -0.80
     perpé
    -0.80
    onomous
    -0.78
     ぱ
    -0.78
    used
    -0.78
     dage
    -0.78
    POSITIVE LOGITS
     bargains
    2.09
     bargain
    2.03
     value
    1.88
     undervalued
    1.62
     attractive
    1.62
     opportunity
    1.50
     cheap
    1.49
     buying
    1.45
     Bargain
    1.41
     Value
    1.35
    Activations Density 0.015%

    No Known Activations